A self-organizing neural scheme for road detection in varied environments

Detection of a drivable space is a key step in the autonomous control of a vehicle. In this paper we propose an adaptive vision based algorithm for road detection in diverse outdoor conditions. Our novel approach employs feature based classification and uses the Kohonen Self-Organizing Map (SOM) for the purpose of road detection. The robustness of the algorithm lies in the unique ability of SOM to organize information while learning diverse inputs. Features used for the training and testing of SOM are identified. The proposed method is capable of working with structured as well as unstructured roads and noisy environments that may be encountered by an intelligent vehicle. The proposed technique is extensively compared with the k-Nearest Neighbor (KNN) algorithm. Results show that SOM outperforms KNN in classification consistency and is independent to the lighting conditions while taking comparable classification time which shows that the network can also be used as an online learning architecture.

[1]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[2]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[3]  Charles E. Thorpe,et al.  SCARF: a color vision system that tracks roads and intersections , 1993, IEEE Trans. Robotics Autom..

[4]  Aya Takeuchi,et al.  Adaptive road detection through continuous environment learning , 2004, 33rd Applied Imagery Pattern Recognition Workshop (AIPR'04).

[5]  Yang Xin,et al.  The Global Road Extraction Approach from Synthetic Aperture Radar Images , 2009, 2009 IEEE Circuits and Systems International Conference on Testing and Diagnosis.

[6]  Massimo Bertozzi,et al.  An Evolutionary Approach to Lane Markings Detection in Road Environments , 2002 .

[7]  Nanning Zheng,et al.  A novel approach of road recognition based on deformable template and genetic algorithm , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[8]  Antonio M. López,et al.  Shadow Resistant Road Segmentation from a Mobile Monocular System , 2007, IbPRIA.

[9]  Guangming Xiong,et al.  Road detection using support vector machine based on online learning and evaluation , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[10]  Dean Pomerleau,et al.  Efficient Training of Artificial Neural Networks for Autonomous Navigation , 1991, Neural Computation.

[11]  Yixin Yin,et al.  Visual information processing using cellular neural networks for mobile robot , 2007, 2007 IEEE International Conference on Grey Systems and Intelligent Services.

[12]  D. Pomerleau,et al.  MANIAC : A Next Generation Neurally Based Autonomous Road Follower , 1993 .

[13]  Bo Zhang,et al.  A neural network approach to the elimination of road shadow for outdoor mobile robot , 1997, 1997 IEEE International Conference on Intelligent Processing Systems (Cat. No.97TH8335).

[14]  Ki-Sang Hong,et al.  Road detection in SAR images using genetic algorithm with region growing concept , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[15]  Rafael Arnay,et al.  Ant colony optimisation algorithm for detection and tracking of non-structured roads , 2008 .

[16]  Charles E. Thorpe,et al.  UNSCARF-a color vision system for the detection of unstructured roads , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[17]  H.-H. Nagel,et al.  Texture-based segmentation of road images , 1994, Proceedings of the Intelligent Vehicles '94 Symposium.

[18]  Fuchun Sun,et al.  Color vision-based multi-level analysis and fusion for road area detection , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[19]  F. Kunwar,et al.  Generic vision based algorithm for driving space detection in diverse indoor and outdoor environments , 2010, 2010 IEEE International Conference on Mechatronics and Automation.